HackerTrans
トップ新着トレンドコメント過去質問紹介求人

yvbbrjdr

no profile record

投稿

NVIDIA DGX Spark In-Depth Review: A New Standard for Local AI Inference

lmsys.org
115 ポイント·投稿者 yvbbrjdr·9 か月前·93 コメント

LMRouter: Run Claude Code on Any LLM with One Command

github.com
1 ポイント·投稿者 yvbbrjdr·11 か月前·0 コメント

コメント

yvbbrjdr
·9 か月前·議論
We actually profiled one of the models, and saw that the last GeMM, which is completely memory bound, is taking a lot of time, which reduces the token speed by a lot.
yvbbrjdr
·9 か月前·議論
I see! Do you know what's causing the slowdown for ollama? They should be using the same backend..
yvbbrjdr
·9 か月前·議論
Hi, author here. I crowd-sourced the devices for benchmarking from my friends. It just happened that none of my friend has this device.
yvbbrjdr
·9 か月前·議論
Hi, author here. I crowd-sourced the devices for benchmarking from my friends. It just happened that one of my friend has this device.